Pinned Loading

1. HELM HELM Public

   HELM is a compiler and runtime for deploying Large Language Models (LLMs) on heterogeneous hardware clusters. It orchestrates execution across GPUs, and CPUs.

   Python 1

2. fast_llm fast_llm Public

   This project focuses on the performance analysis and optimization of Large Language Model (LLM) inference.

   Python 2

3. LLM-Reasoning LLM-Reasoning Public

   Selecting the Hardest-to-Refute Answer: Equilibrium-Based Aggregation for LLM Reasoning

   Python

4. unsupervised_rl_interp unsupervised_rl_interp Public

   A comprehensive interpretability framework for understanding how curiosity-driven agents explore and represent the world in unsupervised reinforcement learning settings.

   Python